© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7023
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    LaTeX commands and mathematical notation

    np_token-act-pair-logits · gpt-4o-mini

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.72
     InputDecoration
    -0.68
    PhysRevLett
    -0.68
    WithIOException
    -0.67
     صوتيه
    -0.66
    MfG
    -0.65
     '\\;'
    -0.65
    EDEFAULT
    -0.64
    enderror
    -0.64
    AutoScaleMode
    -0.64
    POSITIVE LOGITS
    Long
    0.50
    less
    0.50
    in
    0.48
    TableBody
    0.48
    apin
    0.45
     Long
    0.44
     in
    0.44
     Kontexten
    0.42
    ar
    0.41
     ча
    0.41
    Activations Density 1.472%

    No Known Activations